The paper introduces a physics‑driven, cross‑domain iterative framework for self‑supervised low‑dose CT denoising. It first uses a learned sinogram prior and the LDCT noise model to separate Poisson and Gaussian noise components, then applies binomial and Gaussian data thinning to create two training pairs with independent noise realizations. These pairs train an image‑domain network whose outputs are forward‑projected to refine the prior, yielding consistent performance gains over existing self‑supervised baselines and comparable results to supervised methods.
arXiv:2601.14180v5 Announce Type: replace Abstract: Self-supervised learning has been increasingly investigated for low-dose computed tomography (LDCT) image denoising, as it alleviates the dependenc...
Noise2Match is a self‑supervised method for low‑dose CT denoising that uses an adaptive inter‑slice matching network to model and correct the label transition between adjacent slices. By ensuring the equal‑mean condition of the Noise2Noise framework, it theoretically matches supervised training with paired noisy‑clean data. The approach also extends effectively to low‑dose cone‑beam CT, outperforming existing image‑domain self‑supervised methods.
arXiv:2508.17299v2 Announce Type: replace Abstract: Low-dose computed tomography (CT) denoising is crucial for reduced radiation exposure while ensuring diagnostically acceptable image quality. Despi...
arXiv:2607. 11941v1 Announce Type: cross Abstract: Computed tomography (CT) is a critical imaging modality for clinical diagnosis, but reducing radiation dose inevitably introduces severe noise and structured artifacts that degrade image quality.
The paper introduces Dose-Aware Cold Diffusion (DACD), a physics-consistent framework that treats radiation dose as a continuous latent variable in a cold diffusion process for low-dose CT reconstruction. DACD combines dose-aware perception, multi-scale structural priors, and dose-calibrated step allocation to guide denoising, and adds an iterative forward-backprojection correction to enforce projection-domain consistency. Experiments on Mayo-2020, Mayo-2016, and LoDoPaB-CT show DACD outperforms existing diffusion-based and physics-guided methods, especially at ultra-low doses, and generalizes robustly across continuous, unseen dose levels.
arXiv:2608. 08919v1 Announce Type: cross Abstract: During standard radiotherapy planning, repeated CT acquisitions are often required for patient registration, verification, and adaptive planning, resulting in increased cumulative X-ray dose.
arXiv:2605. 24590v2 Announce Type: replace-cross Abstract: Low-light, long-exposure defocus deblurring remains a challenging problem due to the simultaneous presence of severe blur and complex biased noise.
arXiv:2608.10343v2 Announce Type: replace Abstract: While deep learning-based denoising has become widely adopted in low-dose CT, conventional models use generic architectures designed for natural im...
The paper introduces a deep dictionary network (DDN) foundation model designed for ultra‑low‑dose CT (ULDCT) denoising across multiple organs. By cascading convolutional sparse coding layers with iterative soft‑thresholding, the architecture offers inherent interpretability, while dynamic dictionary and threshold modules enhance representation. The model is pre‑trained on over one million normal‑dose CT images and fine‑tuned on multi‑organ ULDCT datasets, achieving state‑of‑the‑art performance that consistently outperforms existing methods.
arXiv:2606. 16212v1 Announce Type: cross Abstract: Sparse-view CT reduces radiation dose and scanning time by acquiring fewer projection views, but angular undersampling makes reconstruction severely ill-posed, causing streak artifacts, structural blurring, and loss of fine details.
arXiv:2509. 21913v2 Announce Type: replace-cross Abstract: Background: Cone-beam computed tomography CBCT is a commonly used modality for image guided radiotherapy.
X-ray computed tomography reconstruction is an ill-posed inverse problem, particularly in low-dose and sparse-angle settings where measurements are noisy and incomplete. While learned reconstruction methods such as the Learned Primal-Dual algorithm achieve strong performance, they typically rely on supervised training with access to ground-truth data, which is often unavailable in practice.